© The Institution of Engineering and Technology
Lung vessel segmentation of computed tomography (CT) images is important in clinical practise and challenging due to difficulties associated with minor size and blurred edges of lung vessels. A vessel segmentation method is proposed for lung images based on a random forest classifier and sparse auto-encoder features. First, the multi-scale representations of lung images are obtained using the Gaussian pyramid. Second, a sparse auto-encoder of three layers is trained using randomly selected patches of these images. Next, the trained weight of the sparse auto-encoder is used as the convolution kernel to extract features of different scale images. Finally, a random forest classifier is exploited to segment the vessels. The proposed method was evaluated on the original and noise-added VESSEL12 dataset that is publicly available. Comparison with some classical methods and existing machine learning methods shows that the proposed method reaches the state-of-the-art accuracy. The results also show that a shallow neural network is a powerful feature extraction tool.
References
-
-
1)
-
4. Frangi, A.F., Niessen, W.J., Vincken, K.L., et al: ‘Multiscale vessel enhancement filtering’. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, Cambridge MA, USA, October 1998, pp. 130–137_3, .
-
2)
-
7. Coates, A., Lee, H., Ng, A.: ‘An analysis of single-layer networks in unsupervised feature learning’, J. Mach. Learn. Res., 2011, 15, pp. 215–223.
-
3)
-
1. Lin, T.H., Zheng, Y.B.: ‘Adaptive image enhancement for retinal blood vessel segmentation’, Electron. Lett., 2002, 38, (19), pp. 1090–1091 (doi: 10.1049/el:20020775).
-
4)
-
8. Ranzato, M.A., Poultney, C., Chopra, S., Cun, Y.L.: ‘Efficient learning of sparse representations with an energy-based model’. Advances in Neural Information Processing Systems, Vancouver, B.C., Canada, December 2006, pp. 1137–1144.
-
5)
-
5. Ochs, R.A., Goldin, J.G., Abtinb, F., Kim, H.J., et al: ‘Automated classification of lung bronchovascular anatomy in CT using AdaBoost’, Med. Image Anal., 2007, 11, (3), pp. 315–324 (doi: 10.1016/j.media.2007.03.004).
-
6)
-
6. Kiros, R., Popuri, K., Cobzas, D., et al: ‘Stacked multiscale feature learning for domain independent medical image segmentation’. Int. Workshop on Machine Learning in Medical Imaging, Boston, MA, USA, September 2014, pp. 25–32, .
-
7)
-
2. Lassen, B., Rikxoort, E.M., Schmidt, M., et al: ‘Automatic segmentation of the pulmonary lobes from chest CT scans based on fissures, vessels, and bronchi’, IEEE Trans. Med. Imaging, 2013, 32, (2), pp. 210–222 (doi: 10.1109/TMI.2012.2219881).
-
8)
-
3. Orkisz, M., Hoyos, M.H., Romanello, V.P., et al: ‘Segmentation of the pulmonary vascular trees in 3D CT images using variational region-growing’, IRBM, 2014, 35, (1), pp. 11–19 (doi: 10.1016/j.irbm.2013.12.001).
-
9)
-
9. Breiman, L.: ‘Random forests’, Mach. Learn, 2001, 45, pp. 5–32 (doi: 10.1023/A:1010933404324).
-
10)
-
10. Ginneken, B., Kerkstra, S., Shneider, C.: ‘VESSEL12 dataset’. .
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2016.4438
Related content
content/journals/10.1049/el.2016.4438
pub_keyword,iet_inspecKeyword,pub_concept
6
6